Detection of knee abnormality from surface EMG signals by artificial neural networks

Erkaymaz, Okan; Senyer, Irem; Uzun, Rukiye

doi:10.1109/siu.2017.7960160

Cited by 5 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tibia, femur, and pattela are the three major bones that are used to form the knee joint. X-Ray, Magnetic Resonance Imaging (MRI), CT, Arthroscopic are the different techniques that are being used to diagnose the knee abnormality clinically [2], [3], [4]. X-Ray is being used for the initial evaluation of knee pain but this technique is not powerful.…”

Section: Introductionmentioning

confidence: 99%

“…The sEMG signals play a critical role in analyzing the lower limb movements and may help in detecting anomalies in the lower limb. Artificial Neural Network based knee abnormality classification has been done by Erkamaz et al [4]. Vijayvargiya et al have been analyzed the early detection of knee osteoarthritis by using support vector machine classifier with different kernels [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis of Machine Learning Techniques for the Classification of Knee Abnormality

Vijayvargiya

Kumar

Dey

et al. 2020

2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA)

View full text Add to dashboard Cite

Knee abnormality is a major problem in elderly people these days. This can be diagnosed by using MRI or X-Ray techniques. X-Ray technique is only be used for the primary evaluation while MRI is an efficient way to diagnose knee abnormality but it is very expensive. In this work, Surface EMG (sEMG) signal taken from healthy and knee abnormal individuals for three different lower limb movements (Gait, Standing and Sitting) were used for the classification. For the classification, first Discrete Wavelet Transform (DWT) was being used for denoising the signal then eleven different time-domain features were extracted by using 256 msec windowing with 25% overlapping. After that normalized the features between 0 to 1 and then selected by using the backward elimination method using the pvalue test. Five different machine learning classifiers (k-nearest neighbor, support vector machine, decision tree, random forest, and extra tree) were tested for this classification by training with selected features. Our result shows that the Extra Tree Classifier with ten cross-validations gives the highest accuracy (91%) to detect the knee abnormality using sEMG signal.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Machine Learning Techniques for the Classification of Knee Abnormality

Vijayvargiya

Kumar

Dey

et al. 2020

2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA)

View full text Add to dashboard Cite

show abstract

“…Neural network has strong nonlinear approximation ability and the ability to deal with unknown internal mechanism problems [31][32][33]. However, the neural network model needs iterative learning in the training process [34], the convergence speed is slow, and the real-time performance needs to be improved [35,36]. e sEMG signal is susceptible to external environmental influences during the acquisition process, such as sweating, muscle fatigue, electrode offset, and power frequency noise [37,38].…”

Section: Introductionmentioning

confidence: 99%

Lower Limb Motion Recognition Method Based on Improved Wavelet Packet Transform and Unscented Kalman Neural Network

Shi

Qin

Zhu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Exoskeleton robot is a typical application to assist the motion of lower limbs. To make the lower extremity exoskeleton more flexible, it is necessary to identify various motion intentions of the lower limbs of the human body. Although more sEMG sensors can be used to identify more lower limb motion intention, with the increase in the number of sensors, more and more data need to be processed. In the process of human motion, the collected sEMG signal is easy to be interfered with noise. To improve the practicality of the lower extremity exoskeleton robot, this paper proposed a wavelet packet transform- (WPT-) based sliding window difference average filtering feature extract algorithm and the unscented Kalman neural network (UKFNN) recognition algorithm. We established an sEMG energy feature model, using a sliding window difference average filtering method to suppress noise interference and extracted stable feature values and using UKF filtering to optimize the neural network weights to improve the adaptability and accuracy of the recognition model. In this paper, we collected the sEMG signals of three muscles to identify six lower limb motion intentions. The average accuracy of 94.83% is proposed in this paper. Experiments show that the algorithm improves the accuracy and anti-interference of motion intention recognition of lower limb sEMG signals. The algorithm is superior to the backpropagation neural network (BPNN) recognition algorithm in the lower limb motion intention recognition and proves the effectiveness, novelty, and reliability of the method in this paper.

show abstract

Knee Abnormality Diagnosis Based on Electromyography Signals

Issa

Khaled

2022

Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021)

View full text Add to dashboard Cite

Detection of knee abnormality from surface EMG signals by artificial neural networks

Cited by 5 publications

References 3 publications

Comparative Analysis of Machine Learning Techniques for the Classification of Knee Abnormality

Comparative Analysis of Machine Learning Techniques for the Classification of Knee Abnormality

Lower Limb Motion Recognition Method Based on Improved Wavelet Packet Transform and Unscented Kalman Neural Network

Knee Abnormality Diagnosis Based on Electromyography Signals

Contact Info

Product

Resources

About